INDEX

Explanations

terms related to governance and political intervention

oai_token-act-pair · gpt-4o-mini Triggered by @bot

history and continuity

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PreferredItem

-0.62

RectangleBorder

-0.57

:✨

-0.52

 MainAxisSize

-0.47

 ControllerBase

-0.46

 cherchés

-0.45

UrlResolution

-0.44

期刊论文

-0.42

GetAsync

-0.41

 BorderRadius

-0.40

POSITIVE LOGITS

歴代

0.46

 siempre

0.46

ždy

0.45

 always

0.45

 zawsze

0.45

 vždy

0.45

 generations

0.44

历

0.43

always

0.43

ništ

0.43

Activations Density 0.142%

terms related to governance and political intervention

history and continuity

No Comments

No Known Activations